© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252026
    Prev
    Next
    INDEX
    Explanations

    specific words and following terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    convers
    0.49
    ماً
    0.44
    seem
    0.44
    мі
    0.43
    offic
    0.43
    К
    0.43
    homeini
    0.42
    _);
    0.42
    inactive
    0.42
    zovaniyu
    0.42
    POSITIVE LOGITS
     reconfiguration
    0.50
    ıl
    0.46
    汅
    0.45
     announc
    0.45
     vandalism
    0.45
    変わり
    0.45
    یت
    0.45
     थी
    0.44
     تھا
    0.44
    ukar
    0.44
    Activations Density 0.001%

    No Known Activations